{ "architectures": [ "T5ForConditionalGeneration" ], "bos_token_id": 1, "d_ff": 3072, "d_kv": 64, "d_model": 768, "decoder_start_token_id": 0, "dropout_rate": 0.1, "eos_token_id": 2, "feed_forward_proj": "relu", "id2label": { "0": "LABEL_0" }, "initializer_factor": 1.0, "is_encoder_decoder": true, "label2id": { "LABEL_0": 0 }, "layer_norm_epsilon": 1e-06, "model_type": "t5", "n_positions": 512, "num_decoder_layers": 12, "num_heads": 12, "num_layers": 12, "output_past": true, "pad_token_id": 0, "relative_attention_num_buckets": 32, "task_specific_params": { "summarization": { "early_stopping": true, "length_penalty": 2.0, "max_length": 256, "min_length": 1, "no_repeat_ngram_size": 3, "num_beams": 5 } }, "transformers_version": "4.5.0", "use_cache": true, "vocab_size": 32100 }